INDEX
Explanations
phrases or words related to immigration
references to immigrants
New Auto-Interp
Negative Logits
ebin
-0.83
yss
-0.80
phasis
-0.77
ategory
-0.76
idges
-0.74
omach
-0.73
izons
-0.72
fax
-0.69
ormal
-0.69
orsche
-0.68
POSITIVE LOGITS
immigrants
1.07
visas
0.89
migrants
0.84
immigrant
0.83
deported
0.82
igrants
0.80
fleeing
0.78
scapego
0.76
seekers
0.75
refugees
0.75
Activations Density 0.020%